Back to Lab
Research Pillar

Intent Understanding & Evolution

Transforming fuzzy human intent into precise behavioral specifications through conversation. This is where the human meets the machine.

Current Frontier

Intent-to-spec translation: converting natural language descriptions into formal behavioral contracts.

Key Questions

01

Can intent be captured precisely enough through conversation alone?

02

How do you handle ambiguity — should the system ask for clarification or make reasonable defaults?

03

How does intent evolve over a session, and how does the system track that evolution?

04

What's the right interface between human intent and machine execution?

Key Papers

PAN: Language-Conditioned World Actions

MBZUAI (Nov 2025)

Natural language control — 'turn left and speed up'. Highest fidelity among open-source models.

Read paper

FOUNDER: Bridging LLMs with World Models

ICML 2025

Bridges LLMs (intent/narrative) with world models (physics/dynamics). THE architecture paper for intent.

Read paper

A2UI Protocol

Google (Dec 2025)

Declarative intent → rendered output protocol. Shows how to structure intent-to-experience pipelines.

Read paper

UniSim: Universal Simulation

DeepMind (ICLR 2024)

Simulates both high-level instructions and low-level controls. Multi-modal intent understanding.

Read paper

GameGen-X: Interactive Game Generation

ICLR 2025

InstructNet for interactive control of generated game content from natural language instructions.

Read paper

Current Insights

Intent exists on a spectrum from vague ('make it nice') to precise ('the button should be 44px, blue, rounded'). The system needs to handle the full spectrum.

Intent evolution — the user changes their mind mid-session — is not an edge case. It's the normal case. The system must handle it gracefully.